针对安徽省气象能见度数据缺测问题，选取安徽省4种不同地形条件下的自动气象站点（黄山站、灵璧站、山南溪谷站、白泽湖站）2017—2019年的气象数据，首先采用灰色关联分析法筛选出与能见度联系紧密的气象要素，然后构建遗传算法（genetic algorithm, GA）和粒子群算法（particle swarm optimization algorithm, PSO）混合算法优化BP（back propagation）神经网络的预测模型，对4种不同地形条件下的自动气象站点的能见度进行预测，并与RF预测模型、XGBoost预测模型的预测效果进行对比，结果表明采用GA-PSO-BP神经网络预测模型无论在哪种地形条件下，预测误差更小，模型精度更高。

In view of the lack of meteorological visibility data in Anhui Province, meteorological data from four automatic meteorological stations (Mount Huangshan Station, Lingbi Station, Shannan Xigu Station, and Baize Lake Station) under different terrain conditions in Anhui Province were selected from the years 2017 to 2019. The meteorological elements closely related to visibility were first identified using the gray correlation analysis method. Subsequently, a hybrid algorithm of genetic algorithm (GA) and particle swarm optimization algorithm (PSO) was employed to optimize the prediction model of the back propagation (BP) neural network. The visibility of automatic weather stations under four different terrain conditions was predicted, and the prediction results were compared with the RF prediction model and XGBoost prediction model. The results indicate that, under any terrain condition, the GA-PSO-BP neural network prediction model exhibits smaller prediction errors and higher model accuracy.